Deep Learning is often depicted as a trio of data-architecture-loss. Yet,
recent Self Supervised Learning (SSL) solutions have introduced numerous
additional design choices, e.g., a projector network, positive views, or
teacher-student networks. These additions pose two challenges. First, they
limit the impact of theoretical studies that often fail to incorporate all
those intertwined designs. Second, they slow-down the deployment of SSL methods
to new domains as numerous hyper-parameters need to be carefully tuned. In this
study, we bring forward the surprising observation that--at least for
pretraining datasets of up to a few hundred thousands samples--the additional
designs introduced by SSL do not contribute to the quality of the learned
representations. That finding not only provides legitimacy to existing
theoretical studies, but also simplifies the practitioner's path to SSL
deployment in numerous small and medium scale settings. Our finding answers a
long-lasting question: the often-experienced sensitivity to training settings
and hyper-parameters encountered in SSL come from their design, rather than the
absence of supervised guidance.

深度学习常被描述为数据 - 架构 - 损失的三位一体。然而，最近的自监督学习 (SSL) 解决方案引入了许多其他设计选择，如投影网络、正向视图或师生网络。本研究的发现是，对于多达几十万个样本的预训练数据集，SSL 引入的额外设计对所学表示的质量没有贡献。这一发现不仅为现有的理论研究提供了正当性，而且简化了在许多小型和中型场景中实施 SSL 的从业者的路径。我们的发现回答了一个长期存在的问题：在 SSL 中遇到的对训练设置和超参数的敏感性来自其设计，而不是缺乏监督指导。

奥卡姆剃刀原则在自监督学习中的应用：什么是足够的学习良好的特征表示？

Occam's Razor for Self Supervised Learning: What is Sufficient to Learn  Good Representations?

Limit order books (LOBs) match buyers and sellers in more than half of the
world's financial markets. This survey highlights the insights that have
emerged from the wealth of empirical and theoretical studies of LOBs. We
examine the findings reported by statistical analyses of historical LOB data
and discuss how several LOB models provide insight into certain aspects of the
mechanism. We also illustrate that many such models poorly resemble real LOBs
and that several well-established empirical facts have yet to be reproduced
satisfactorily. Finally, we identify several key unresolved questions about
LOBs.

本文概述了大量实证和理论研究在限价订单簿上取得的洞见，探讨了统计分析历史价位和数量数据所报告的研究结果，说明了许多 LOB 模型并不像真实 LOB 一样。此外，我们还发现了一些关键未解决问题。